Yuki Takezawa

34 papers A* 7A 1Journal 25Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
A Bias Correction Mechanism for Distributed Asynchronous Optimization.
Trans. Mach. Learn. Res.
Yuan Gao, Yuki Takezawa, Sebastian U. Stich
2025 J jnl
Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses.
CoRR
Han Bao, Shinsaku Sakaue, Yuki Takezawa
2025 J jnl
Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation.
CoRR
Kaoru Otsuka, Yuki Takezawa, Makoto Yamada
2025 A* conf
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization.
ICML
Yuki Takezawa, Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
2025 J jnl
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization.
CoRR
Yuki Takezawa, Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
2025 J jnl
FedMuon: Federated Learning with Bias-corrected LMO-based Optimization.
CoRR
Yuki Takezawa, Anastasia Koloskova, Xiaowen Jiang, Sebastian U. Stich
2025 J jnl
Necessary and Sufficient Watermark for Large Language Models.
Trans. Mach. Learn. Res.
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
2025 A* conf
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis.
ICLR
Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa
2025 A* conf
Scalable Decentralized Learning with Teleportation.
ICLR
Yuki Takezawa, Sebastian U. Stich
2025 J jnl
Scalable Decentralized Learning with Teleportation.
CoRR
Yuki Takezawa, Sebastian U. Stich
2024 J jnl
A Localized Primal-Dual Method for Centralized/Decentralized Federated Learning Robust to Data Heterogeneity.
IEEE Trans. Signal Inf. Process. over Networks
Iifan Tyou, Tomoya Murata, Takumi Fukami, Yuki Takezawa, Kenta Niwa
2024 J jnl
An Empirical Study of Self-Supervised Learning with Wasserstein Distance.
Entropy
Makoto Yamada, Yuki Takezawa, Guillaume Houry, Kira Michaela Düsterwald, Déborah Sulem, Han Zhao, Yao-hung Tsai
2024 A* conf
Parameter-free Clipped Gradient Descent Meets Polyak.
NeurIPS
Yuki Takezawa, Han Bao, Ryoma Sato, Kenta Niwa, Makoto Yamada
2024 J jnl
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis.
CoRR
Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa
2024 J jnl
Polyak Meets Parameter-free Clipped Gradient Descent.
CoRR
Yuki Takezawa, Han Bao, Ryoma Sato, Kenta Niwa, Makoto Yamada
2023 J jnl
An Empirical Study of Simplicial Representation Learning with Wasserstein Distance.
CoRR
Makoto Yamada, Yuki Takezawa, Guillaume Houry, Kira Michaela Dusterwald, Déborah Sulem, Han Zhao, Yao-Hung Hubert Tsai
2023 A* conf
Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence.
NeurIPS
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
2023 J jnl
Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence.
CoRR
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
2023 J jnl
Communication Compression for Decentralized Learning With Operator Splitting Methods.
IEEE Trans. Signal Inf. Process. over Networks
Yuki Takezawa, Kenta Niwa, Makoto Yamada
2023 J jnl
Embarrassingly Simple Text Watermarks.
CoRR
Ryoma Sato, Yuki Takezawa, Han Bao, Kenta Niwa, Makoto Yamada
2023 — conf
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following.
MMM (2)
Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2023 A* conf
Large-scale similarity search with Optimal Transport.
EMNLP
Cléa Laouar, Yuki Takezawa, Makoto Yamada
2023 J jnl
Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data.
Trans. Mach. Learn. Res.
Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada
2023 J jnl
Necessary and Sufficient Watermark for Large Language Models.
CoRR
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
2022 J jnl
Approximating 1-Wasserstein Distance with Trees.
CoRR
Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi
2022 J jnl
Approximating 1-Wasserstein Distance with Trees.
Trans. Mach. Learn. Res.
Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi
2022 J jnl
Communication Compression for Decentralized Learning with Operator Splitting Methods.
CoRR
Yuki Takezawa, Kenta Niwa, Makoto Yamada
2022 A conf
Fixed Support Tree-Sliced Wasserstein Barycenter.
AISTATS
Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada
2022 J jnl
Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data.
CoRR
Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada
2022 J jnl
Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization.
CoRR
Yuki Takezawa, Kenta Niwa, Makoto Yamada
2021 J jnl
Fixed Support Tree-Sliced Wasserstein Barycenter.
CoRR
Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada
2021 J jnl
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following.
CoRR
Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2021 A* conf
Supervised Tree-Wasserstein Distance.
ICML
Yuki Takezawa, Ryoma Sato, Makoto Yamada
2021 J jnl
Supervised Tree-Wasserstein Distance.
CoRR
Yuki Takezawa, Ryoma Sato, Makoto Yamada